Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/sifxprime/kodelyth-ecc/project-launchgit clone --depth 1 https://github.com/sifxprime/kodelyth-eccWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/sifxprime/kodelyth-ecc/project-launch)<a href="https://agentmods.dev/commands/sifxprime/kodelyth-ecc/project-launch"><img src="https://agentmods.dev/badge/commands/sifxprime/kodelyth-ecc/project-launch.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00033 | $0.00803 |
| Opus 5 | $0.00016 | $0.00402 |
| Sonnet 5 | $0.00007 | $0.00161 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
project-launch scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/project-launch — Parallel Founding Team
Launch all founding-team agents in parallel on your new project. What would take 40+ minutes sequentially finishes in under 10 minutes as one parallel burst.
Usage
/project-launch <description>
/project-launch "SaaS dashboard with Stripe billing, user auth, real-time data"
/project-launch --full # adds performance-optimizer and api-guardian to the team
What Gets Launched in Parallel
Five specialist agents fire simultaneously, each with the same project description:
| Agent | Deliverable |
|---|---|
architect |
System design — components, data flow, boundaries, trade-offs |
pair-programmer |
Approach validation — risks, wrong turns, questions to answer before coding |
security-reviewer |
Threat model — auth, data exposure, OWASP risks for THIS project type |
tdd-guide |
Test strategy — what to test first, test pyramid, critical paths |
ux-reviewer |
UX blueprint — user flows, accessibility requirements, interaction risks |
With --full, also adds:
performance-optimizer— scaling bottlenecks, caching strategy, query patternsapi-guardian— API contract design, versioning strategy, breaking change risks
How It Works
- Read the project description from
$ARGUMENTS - If no description provided, ask for one in one sentence
- Spawn all 5 (or 7) agents simultaneously with
run_in_background: true - Each agent receives: the project description + its specialist brief
- Wait for all to complete
- Aggregate results into a structured Project Launch Report:
## PROJECT LAUNCH REPORT
### Architecture (architect)
[findings]
### Approach Risks (pair-programmer)
[findings]
### Threat Model (security-reviewer)
[findings]
### Test Strategy (tdd-guide)
[findings]
### UX Blueprint (ux-reviewer)
[findings]
- After report: ask "Which area do you want to go deeper on first?"
Token Efficiency
Each agent gets a narrow, focused context — just the project description + its specialist instructions. No agent carries the full conversation history. The system prompt (rules + agents) is cached across all parallel agents. Result: 5× the analysis at roughly 2× the token cost of a single sequential session.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 92 lines · 33 tokens per session scan A 07bac3c45318
project-launch is a command published in the GitHub repository sifxprime/kodelyth-ecc (11 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 803 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
toh-help
Display all Toh Framework commands and quick usage guide.
opsx-new
Start a new change using the experimental artifact workflow (OPSX).
research
Delegate a thorough research investigation to the agy:runner subagent.
experiment
Design A/B test with statistical rigor. Usage: /mindforge:experiment [feature] [--metric conversion|engagement|revenue] [--duration 2w].
kimi-setup
Run node "$HOME/.kimi-plugin/kimi-companion.mjs" setup, then report installation and authentication status.
strategy-cfo
商业战略与财商融合决策专家 — 商业模式 / 资本结构 / 投资决策 / 资源配置 / 估值视角.